Reducing False Positives in Deep Learning-based Brain Metastasis Detection by Using Both Gradient-echo and Spin-echo Contrast-enhanced MRI: Validation in a Multi-center Diagnostic Cohort

Overview

Journal Eur Radiol

Specialty Radiology

Date 2023 Oct 27

PMID 37891415

Authors

Suyoung Yun

Ji Eun Park

NakYoung Kim

Seo Young Park

Ho Sung Kim

Affiliations

Soon will be listed here.

Abstract

Objectives: To develop a deep learning (DL) for detection of brain metastasis (BM) that incorporates both gradient- and turbo spin-echo contrast-enhanced MRI (dual-enhanced DL) and evaluate it in a clinical cohort in comparison with human readers and DL using gradient-echo-based imaging only (GRE DL).

Materials And Methods: DL detection was developed using data from 200 patients with BM (training set) and tested in 62 (internal) and 48 (external) consecutive patients who underwent stereotactic radiosurgery and diagnostic dual-enhanced imaging (dual-enhanced DL) and later guide GRE imaging (GRE DL). The detection sensitivity and positive predictive value (PPV) were compared between two DLs. Two neuroradiologists independently analyzed BM and reference standards for BM were separately drawn by another neuroradiologist. The relative differences (RDs) from the reference standard BM numbers were compared between the DLs and neuroradiologists.

Results: Sensitivity was similar between GRE DL (93%, 95% confidence interval [CI]: 90-96%) and dual-enhanced DL (92% [89-94%]). The PPV of the dual-enhanced DL was higher (89% [86-92%], p < .001) than that of GRE DL (76%, [72-80%]). GRE DL significantly overestimated the number of metastases (false positives; RD: 0.05, 95% CI: 0.00-0.58) compared with neuroradiologists (RD: 0.00, 95% CI: - 0.28, 0.15, p < .001), whereas dual-enhanced DL (RD: 0.00, 95% CI: 0.00-0.15) did not show a statistically significant difference from neuroradiologists (RD: 0.00, 95% CI: - 0.20-0.10, p = .913).

Conclusion: The dual-enhanced DL showed improved detection of BM and reduced overestimation compared with GRE DL, achieving similar performance to neuroradiologists.

Clinical Relevance Statement: The use of deep learning-based brain metastasis detection with turbo spin-echo imaging reduces false positive detections, aiding in the guidance of stereotactic radiosurgery when gradient-echo imaging alone is employed.

Key Points: •Deep learning for brain metastasis detection improved by using both gradient- and turbo spin-echo contrast-enhanced MRI (dual-enhanced deep learning). •Dual-enhanced deep learning increased true positive detections and reduced overestimation. •Dual-enhanced deep learning achieved similar performance to neuroradiologists for brain metastasis counts.

Citing Articles

Metastatic brain tumors: from development to cutting-edge treatment.

Tanzhu G, Chen L, Ning J, Xue W, Wang C, Xiao G MedComm (2020). 2024; 6(1):e70020.

PMID: 39712454 PMC: 11661909. DOI: 10.1002/mco2.70020.

References

Kaufmann T, Smits M, Boxerman J, Huang R, Barboriak D, Weller M . Consensus recommendations for a standardized brain tumor imaging protocol for clinical trials in brain metastases. Neuro Oncol. 2020; 22(6):757-772. PMC: 7283031. DOI: 10.1093/neuonc/noaa030. View

Komada T, Naganawa S, Ogawa H, Matsushima M, Kubota S, Kawai H . Contrast-enhanced MR imaging of metastatic brain tumor at 3 tesla: utility of T(1)-weighted SPACE compared with 2D spin echo and 3D gradient echo sequence. Magn Reson Med Sci. 2008; 7(1):13-21. DOI: 10.2463/mrms.7.13. View

Park J, Kim E . Contrast-enhanced, three-dimensional, whole-brain, black-blood imaging: application to small brain metastases. Magn Reson Med. 2010; 63(3):553-61. DOI: 10.1002/mrm.22261. View

Nagao E, Yoshiura T, Hiwatashi A, Obara M, Yamashita K, Kamano H . 3D turbo spin-echo sequence with motion-sensitized driven-equilibrium preparation for detection of brain metastases on 3T MR imaging. AJNR Am J Neuroradiol. 2011; 32(4):664-70. PMC: 7965899. DOI: 10.3174/ajnr.A2343. View

Suh C, Jung S, Kim K, Pyo J . The detectability of brain metastases using contrast-enhanced spin-echo or gradient-echo images: a systematic review and meta-analysis. J Neurooncol. 2016; 129(2):363-71. DOI: 10.1007/s11060-016-2185-y. View

Zhang M, Young G, Chen H, Li J, Qin L, McFaline-Figueroa J . Deep-Learning Detection of Cancer Metastases to the Brain on MRI. J Magn Reson Imaging. 2020; 52(4):1227-1236. PMC: 7487020. DOI: 10.1002/jmri.27129. View

Soliman H, Das S, Larson D, Sahgal A . Stereotactic radiosurgery (SRS) in the modern management of patients with brain metastases. Oncotarget. 2016; 7(11):12318-30. PMC: 4914287. DOI: 10.18632/oncotarget.7131. View

Lippitz B, Lindquist C, Paddick I, Peterson D, ONeill K, Beaney R . Stereotactic radiosurgery in the treatment of brain metastases: the current evidence. Cancer Treat Rev. 2013; 40(1):48-59. DOI: 10.1016/j.ctrv.2013.05.002. View

Zhou Z, Sanders J, Johnson J, Gule-Monroe M, Chen M, Briere T . Computer-aided Detection of Brain Metastases in T1-weighted MRI for Stereotactic Radiosurgery Using Deep Learning Single-Shot Detectors. Radiology. 2020; 295(2):407-415. PMC: 8287889. DOI: 10.1148/radiol.2020191479. View

10.

Cho S, Sunwoo L, Baik S, Bae Y, Choi B, Kim J . Brain metastasis detection using machine learning: a systematic review and meta-analysis. Neuro Oncol. 2020; 23(2):214-225. PMC: 7906058. DOI: 10.1093/neuonc/noaa232. View

11.

Yin S, Luo X, Yang Y, Shao Y, Ma L, Lin C . Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study. Neuro Oncol. 2022; 24(9):1559-1570. PMC: 9435500. DOI: 10.1093/neuonc/noac025. View

12.

Charron O, Lallement A, Jarnet D, Noblet V, Clavier J, Meyer P . Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network. Comput Biol Med. 2018; 95:43-54. DOI: 10.1016/j.compbiomed.2018.02.004. View

13.

Dikici E, Ryu J, Demirer M, Bigelow M, White R, Slone W . Automated Brain Metastases Detection Framework for T1-Weighted Contrast-Enhanced 3D MRI. IEEE J Biomed Health Inform. 2020; 24(10):2883-2893. DOI: 10.1109/JBHI.2020.2982103. View

14.

Grovik E, Yi D, Iv M, Tong E, Rubin D, Zaharchuk G . Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI. J Magn Reson Imaging. 2019; 51(1):175-182. PMC: 7199496. DOI: 10.1002/jmri.26766. View

15.

Xue J, Wang B, Ming Y, Liu X, Jiang Z, Wang C . Deep learning-based detection and segmentation-assisted management of brain metastases. Neuro Oncol. 2019; 22(4):505-514. PMC: 7158643. DOI: 10.1093/neuonc/noz234. View

16.

Park Y, Jun Y, Lee Y, Han K, An C, Ahn S . Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging. Eur Radiol. 2021; 31(9):6686-6695. DOI: 10.1007/s00330-021-07783-3. View

17.

Kikuchi Y, Togao O, Kikuchi K, Momosaka D, Obara M, Van Cauteren M . A deep convolutional neural network-based automatic detection of brain metastases with and without blood vessel suppression. Eur Radiol. 2022; 32(5):2998-3005. DOI: 10.1007/s00330-021-08427-2. View

18.

Park S, Han K . Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction. Radiology. 2018; 286(3):800-809. DOI: 10.1148/radiol.2017171920. View

19.

Park S . Diagnostic Case-Control versus Diagnostic Cohort Studies for Clinical Validation of Artificial Intelligence Algorithm Performance. Radiology. 2018; 290(1):272-273. DOI: 10.1148/radiol.2018182294. View

20.

Tatsuno S, Hata Y, Tada S . [Double-dose Gd-DTPA: detectability of intraparenchymal brain metastasis]. Nihon Igaku Hoshasen Gakkai Zasshi. 1996; 56(12):855-9. View